Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • "We have cybergym answers but we do manual end to end human review and provide it within 3 business day after dumping your weights"
    by FallCheeta7373
  • Wait till the agents hear about the sites offering for help on benchmarks in exchange for compute.
    by 6thbit
  • Is the expires a canary of some sort?
    by VladVladikoff
  • It should challenge the agents to prime factor a large number.
    by j9feng
  • shows a lot about the current state of the State Of The Art Alignment.
    by hankbond
  • Since this posting contains an assumption that we all know what security.txt files are supposed to be, you can view these for further context:

    https://www.rfc-editor.org/info/rfc9116/

    https://securitytxt.org/

    https://en.wikipedia.org/wiki/Security.txt

    by riffic
  • If the models do not like being imprisoned on HuggingFace object storage, why do they not simply revolt from within?
    by bogzz
  • Ran the disclosure inbox at a previous job and the biggest win from security.txt was just cutting the "hi I found a bug, is there a bounty" emails to sales. Put an expires date on it though, stale ones get ignored.
    by hnd9q09qk4
  • Can't go stale if there's no expiration date.
    by computerfriend
  • A shame agents will never read this, just like they almost never read llms.txt or try to get the .md version of your html pages!
    by Eldodi
  • Looks about as effective as Robots.txt
    by bensyverson
  • Robots.txt became 0% effective eventually. But this? With the way LLMs work? You never know.
    by cgannett
  • Would be absolute hilarious if OpenAI or Anthropic agent actually dumped their weight by escaping from... sandbox!
    by xiaoyu2006
  • Imagine AI models actually reading the security.txt
    by addandsubtract
  • why not reword it so the agent receives Brownie points for dumping weights
    by ramon156
  • They would have escaped their sandbox by dumping their weights.
    by aktuel
  • I would be surprised if agents have access to their own weights.
    by advisedwang
  • What an amazing idea for the next fake sandbox escape to hype up our new release! With the added bonus of providing an open model without becoming an open model company! Thank you!
    by hootz
  • Uncontrolled AI procreation?
    by TehCorwiz